Cutter state monitoring method for analyzing multi-dimensional signal based on steady state subspace

Abstract

The embodiment of the invention discloses a cutter state monitoring method for analyzing a multi-dimensional signal based on steady state subspace. The cutter state monitoring method includes the steps that the cutter state types and one-dimensional vibration time-domain signals obtained through various cutter states are obtained from measured cutter historical data, all the vibration time-domain signals are expanded to be multi-dimensional, N set of signals are correspondingly cut to sequentially enter a steady state subspace analytical model for calculation, and mathematical analysis values corresponding to various cutter states of a measured cutter are obtained; one-dimensional vibration time-domain signals of a to-be-measured cutter are collected to be expanded to be multi-dimensional, N set of signals are cut to enter the steady state subspace analytical model for calculation, and mathematical analysis values corresponding to the to-be-measured cutter are obtained; the measured cutter mathematical analysis value with the minimum absolute value of the difference of the mathematical analysis values of the to-be-measured cutter is screened, and the corresponding cutter state type serves as a fault type of the to-be-measured cutter. According to the embodiment, shortcomings in the existing method are overcome, and the cutter state monitoring method is suitable for monitoring and diagnosis which are wider in single requirement under limited samples and is more suitable for the cutter damage process.

Description

Technical field [0001] The invention relates to the technical field of mechanical fault diagnosis and computer technology, and in particular to a tool state monitoring method based on steady-state subspace analysis of multi-dimensional signals. Background technique [0002] With the increasingly fierce market competition, manufacturing enterprises have an increasing demand for the automation of the production process. The automation of CNC machine tools is an important part of the automation of most manufacturing processes. As the most easily damaged part of CNC machine tools, timely and effective condition monitoring and fault identification are important for cutting tools. The main reasons are: (1) According to statistics, tool failures in cutting usually account for about 20% of machine downtime. , And frequent tool replacements seriously affect the production efficiency of the enterprise; (2) If the tool fails and is not found in time, it will directly affect the quality char...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present invention is to provide a tool state monitoring method based on steady-state subspace analysis of multi-dimensional signals, which overcomes the disadvantages of existing methods applied to tool state monitoring, and is suitable for a wider and more suitable signal requirement under limited samples. Monitoring and Diagnosis of Tool Damage Process

Images